CN210667779U - Equipment capable of reducing noise - Google Patents
Equipment capable of reducing noise Download PDFInfo
- Publication number
- CN210667779U CN210667779U CN201920797332.5U CN201920797332U CN210667779U CN 210667779 U CN210667779 U CN 210667779U CN 201920797332 U CN201920797332 U CN 201920797332U CN 210667779 U CN210667779 U CN 210667779U
- Authority
- CN
- China
- Prior art keywords
- noise
- sound
- signal
- module
- external
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The utility model discloses a can realize falling equipment of making an uproar, this equipment includes: the device comprises a first sound acquisition module, a second sound acquisition module, a shell and a noise processing module; the first sound acquisition module is arranged inside the shell and is insulated from the outside of the equipment; the first sound acquisition module is used for acquiring an internal noise signal inside the equipment and sending the internal noise signal to the noise processing module; the second sound acquisition module is used for acquiring a sound input signal outside the equipment and sending the sound input signal to the noise processing module; the noise processing module is also used for acquiring an external noise signal outside the equipment and sending the external noise signal to the noise processing module; and the noise processing module is used for carrying out noise reduction processing on the sound input signal according to the external noise signal and the internal noise signal to obtain a target sound signal. The utility model provides the high intelligence of effect and equipment of falling the noise treatment.
Description
Technical Field
The application relates to the technical field of sound processing, in particular to a device capable of achieving noise reduction.
Background
With the development of artificial intelligence technology, more and more intelligent voice devices appear in people's lives. In order to ensure the accuracy of speech recognition and improve the intelligence of the device, the intelligent device needs to perform noise reduction processing on the received speech. However, when the existing smart device performs noise reduction processing, a single-channel noise reduction mode is usually adopted to eliminate the external ambient noise of the device, and the noise reduction effect is not good.
SUMMERY OF THE UTILITY MODEL
In view of this, the embodiment of the present application provides a device capable of reducing noise, which can solve the problem of poor noise reduction effect of a single channel noise reduction mode in the prior art.
The device that can realize making an uproar that this application embodiment provided includes: the device comprises a first sound acquisition module, a second sound acquisition module, a shell and a noise processing module;
the first sound acquisition module is arranged inside the shell and is in sound insulation with the outside of the equipment; the first sound acquisition module is used for acquiring an internal noise signal inside the equipment and sending the internal noise signal to the noise processing module;
the second sound acquisition module is used for acquiring a sound input signal outside the equipment and sending the sound input signal to the noise processing module; the noise processing module is also used for acquiring an external noise signal outside the equipment and sending the external noise signal to the noise processing module;
and the noise processing module is used for carrying out noise reduction processing on the sound input signal according to the external noise signal and the internal noise signal to obtain a target sound signal.
Optionally, the noise processing module includes: an external noise processing submodule and an internal noise processing submodule;
the external noise processing submodule is used for carrying out noise reduction processing on the sound input signal according to the external noise signal to obtain an external target sound signal;
and the internal noise processing submodule is used for carrying out noise reduction processing on the external target sound signal according to the internal noise signal to obtain the target sound signal.
Optionally, the housing is acoustically insulating.
Optionally, the second sound obtaining module is specifically configured to receive an initial sound signal input from the outside, and perform noise reduction processing on the initial sound signal to obtain the sound input signal.
Optionally, the noise processing module performs noise reduction processing by using a fixed beam form or an adaptive filter.
Optionally, the first sound obtaining module performs noise reduction processing by using a fixed beam form or an adaptive filter.
Compared with the prior art, the method has the advantages that:
in the embodiment of the application, a first sound acquisition module which is soundproof with the outside of the device is arranged inside a shell of the device, the first sound acquisition module can be used for acquiring an internal noise signal inside the device, a second sound acquisition module is used for acquiring an external noise signal and a sound input signal outside the device, the acquired sound input signal, the external noise signal and the internal noise signal are sent to a noise processing module, the noise processing module performs noise reduction processing on the sound input signal according to the external noise signal and the internal noise signal to obtain a target sound signal, the influence of the internal noise of the device on the accuracy of voice recognition of the device is avoided, and the noise reduction processing effect and the intelligence of the device are improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic structural diagram of a noise reduction apparatus provided in an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
When speech recognition is realized, the intelligent device generally performs noise reduction processing on input speech so as to ensure the accuracy of the speech recognition. However, smart devices currently generally employ single-channel noise reduction processing to remove only noise external to the device (e.g., ambient noise). The inventor of the application finds in research that when the internal noise of the intelligent device is large, the internal noise of the intelligent device has large interference on voice recognition, the accuracy of the voice recognition cannot be guaranteed, and the intelligent degree of the intelligent device is low.
Therefore, the device capable of reducing the noise is provided by the embodiment of the application, not only can the external noise of the device be eliminated, but also the internal noise signal of the device can be acquired by utilizing the first sound acquisition module arranged inside the device, so that the internal noise of the device is eliminated, the noise elimination effect and the accuracy of voice recognition are improved, and the high intelligence of the device is ensured.
Based on the above-mentioned ideas, in order to make the above-mentioned objects, features and advantages of the present application more comprehensible, specific embodiments of the present application are described in detail below with reference to the accompanying drawings.
In a specific application scenario of the embodiment of the application, the device capable of achieving noise reduction may be any device capable of performing voice recognition or voice control, including but not limited to a smart phone, a smart sound, a smart home device (such as a sweeping robot, an air purifier, an air conditioner, a fan, etc.), an intelligent translator, etc., and is not limited herein.
Referring to fig. 1, the drawing is a schematic structural diagram of a device capable of reducing noise according to an embodiment of the present application.
The device that can realize making an uproar that this application embodiment provided includes: a first sound acquisition module 110, a second sound acquisition module 120, a housing 130, and a noise processing module 140;
the first sound acquiring module 110 is configured to acquire an internal noise signal inside the device and send the internal noise signal to the noise processing module 140.
In the embodiment of the present application, the first sound acquiring module 110 is disposed inside the housing 130, and the first sound acquiring module 110 is isolated from the outside of the noise reduction enabled device to ensure the accuracy of acquiring the internal noise signal. As will be appreciated, the internal noise signal may be noise generated inside the apparatus by operating noise of devices inside the apparatus that can achieve noise reduction, or the like.
In practical applications, in order to further improve the noise reduction effect, the first sound acquiring module 110 may be configured to be highly isolated from the external sound of the device capable of reducing noise, such as configuring the housing 130 as a sound insulation housing, or add a sound insulation mechanism to the first sound acquiring module 110 inside the housing 130, so that the first sound acquiring module 110 only receives the sound signal inside the device (i.e., the internal noise signal).
It should be noted that the first sound acquiring module 110 may include at least one sound receiving device (such as a microphone with any structure, etc.), and the position and arrangement of the at least one sound receiving device inside the housing 130 may be specifically set according to actual situations, for example, the first sound acquiring module 110 may include a plurality of microphones disposed inside the device in a surrounding arrangement, which is not limited and is not listed here.
A second sound obtaining module 120, configured to obtain a sound input signal external to the device, and send the sound input signal to the noise processing module 140; and is also used to acquire an external noise signal external to the device and send the external noise signal to the noise processing module 140.
In the embodiment of the present application, the second sound acquiring module 120 may be disposed outside the noise reduction enabled device (e.g., outside the housing 130 or on the housing 130), or may be disposed inside the noise reduction enabled device, and fig. 1 only illustrates that the second sound acquiring module 120 is disposed outside the housing 130, which is not limited herein.
Similar to the first sound capture module 110, the second sound capture module 120 may also include one or more sound receiving devices (e.g., a microphone of any configuration, etc.). In practical applications, the position and arrangement of the sound receiving device included in the second sound acquiring module 120 on the device capable of reducing noise may be specifically set according to actual situations and needs. For example, the second sound acquiring module 120 may be an external microphone, or may be a microphone disposed on the housing 130, and the second sound acquiring module 120 may further include a plurality of microphones arranged on the housing 130 in a surrounding manner, and so on, which are not listed here.
It should be noted that the second sound obtaining module 120 may receive a sound signal from outside the noise reduction enabled device, such as a voice command (i.e., a target sound signal desired to be recognized) entered by a user and an external noise signal (e.g., an ambient noise), and the like. In the embodiment of the present application, the sound input signal received by the second sound obtaining module 120 includes not only the external noise signal but also the target sound signal that is expected to be identified.
It should be further noted that, in a specific implementation, the second sound obtaining module 120 and the first sound obtaining module 110 may be connected in parallel, that is, an output end of the second sound obtaining module 120 and an output end of the first sound obtaining module 110 are respectively connected to an input end of the noise processing module 140; the second sound obtaining module 120 and the first sound obtaining module 110 may also be connected in series, that is, the output end of the second sound obtaining module 120 is connected to the input end of the first sound obtaining module 110, and the output end of the first sound obtaining module 110 is connected to the input end of the noise processing module 140; alternatively, the output end of the first sound acquiring module 110 is connected to the input end of the second sound acquiring module 120, and the output end of the second sound acquiring module 120 is connected to the input end of the noise processing module 140, which is not limited herein.
In some possible implementation manners of the embodiment of the application, in order to improve a noise reduction effect, the second sound obtaining module 120 may perform pre-noise reduction on the received sound signal, and then the second sound obtaining module 120 may be specifically configured to receive an initial sound signal input from the outside, and perform noise reduction processing on the initial sound signal to obtain a sound input signal.
It will be appreciated that the initial sound signal may be the original sound signal received directly. In practical applications, any noise reduction algorithm may be used to reduce noise of the initial sound signal, for example, the second sound obtaining module may perform noise reduction processing using a fixed beam form or an adaptive filter. The fixed beam forming means that the filter weight is fixed and unchanged in the beam forming process. Once the geometry of the microphone array, the target direction, is determined, its beam pattern characteristics will also be determined. The method has the advantages of simplicity and low computation. The following will describe the noise reduction processing in detail by way of example, and will not be described herein again.
It should be further noted that the second sound obtaining module 120 may perform parallel noise reduction processing on the obtained sound input signal and the external noise signal to improve efficiency.
And the noise processing module 140 is configured to perform noise reduction processing on the sound input signal according to the external noise signal and the internal noise signal to obtain a target sound signal.
In the embodiment of the application, the external noise signal can be used as a reference signal for eliminating the external noise of the equipment, so that the influence of the external noise of the equipment on the voice recognition is eliminated; and the internal noise signal can be used as a reference signal for eliminating the internal noise of the device so as to eliminate the influence of the internal noise of the device on the speech recognition. Therefore, the noise processing module 140 performs noise reduction processing on the sound input signal according to the acquired external noise signal and internal noise signal, so as to obtain a target sound signal after noise reduction, eliminate the influence of the external noise and the internal noise, improve the accuracy of voice recognition, and ensure high intelligence of the device.
In practical applications, the noise processing module 140 may perform the noise reduction processing by using any noise reduction algorithm, for example, the noise processing module may perform the noise reduction processing by using a fixed beam form or an adaptive filter, which is not limited herein. As one example, noise processing module 140 may perform noise reduction processing using a Least Mean Square (LMS) adaptive filter, a Normalized Least Mean Square (NLMS) adaptive filter, a recursive least mean square (RLS) adaptive filter, or the like.
The principle of the LMS adaptive filter is as follows: the current filter parameters are automatically adjusted by using the filter parameters obtained at the previous moment, so that the input signal sequence x (n) and the expected output signal d (n) are approximated to adapt to the unknown or randomly-changed statistical characteristics of signals and noise, and the optimal filtering is realized.
An error signal e (n) having an input signal sequence of x (n) and a desired output signal of d (n) is expressed by the following equation (1),
in the formula, ωiAs a weight coefficient, n ∈ [1, M ∈ >]。
The essence of the LMS algorithm is to find the optimal weight coefficient, and through a series of derivation, the following formula (2) can be obtained,
ωk(n)＝ωk(n-1)+μe(n)x(n) (2)
where μ is the convergence factor and the size of μ determines the stability and convergence rate of the system. The principle of other adaptive filters is similar to that of LMS, and the difference is only that the standard for approximating the input signal sequence x (n) and the desired output signal d (n) is different, and the details are not repeated here.
In practical applications, the noise processing module 140 may be disposed inside or outside the housing 130 or on the housing 130, which is not limited herein.
In some possible implementation manners of the embodiment of the present application, the noise processing module 140 may include: an external noise processing submodule and an internal noise processing submodule;
the external noise processing submodule is used for carrying out noise reduction processing on the sound input signal according to the external noise signal to obtain an external target sound signal;
and the internal noise processing submodule is used for carrying out noise reduction processing on the external target sound signal according to the internal noise signal to obtain a target sound signal.
In this embodiment of the present application, the noise processing module 140 first performs noise reduction processing on the sound input signal by using an external noise signal, and eliminates the external noise of the noise-reducible device to obtain an external target sound signal; and then, the internal noise signal is utilized to perform noise reduction processing on the obtained external target sound signal, the internal noise of the noise-reducing device is eliminated, an expected target sound signal is obtained, the interference of the external noise is eliminated, the interference of the internal noise is also eliminated, the noise reduction effect and the accuracy of voice recognition are improved, and the high intelligence of the device is ensured. For the description of the noise processing method, reference may be made to the above-mentioned related contents, and details are not repeated here.
In the embodiment of the application, a first sound acquisition module is arranged inside a shell of the device, the first sound acquisition module is insulated from the outside of the device, then the first sound acquisition module can be used for acquiring an internal noise signal inside the device, a second sound acquisition module is used for acquiring an external noise signal and a sound input signal outside the device, the acquired sound input signal, the external noise signal and the internal noise signal are sent to a noise processing module, the noise processing module performs noise reduction processing on the sound input signal according to the external noise signal and the internal noise signal to obtain a target sound signal, the influence of internal noise of the device on the accuracy of voice recognition of the device is avoided, and the effect of noise reduction processing and the intelligence of the device are improved.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing is merely a preferred embodiment of the present application and is not intended to limit the present application in any way. Although the present application has been described with reference to the preferred embodiments, it is not intended to limit the present application. Those skilled in the art can now make numerous possible variations and modifications to the disclosed embodiments, or modify equivalent embodiments, using the methods and techniques disclosed above, without departing from the scope of the claimed embodiments. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application still fall within the protection scope of the technical solution of the present application without departing from the content of the technical solution of the present application.
Claims (6)
1. An apparatus capable of reducing noise, the apparatus comprising: the device comprises a first sound acquisition module, a second sound acquisition module, a shell and a noise processing module;
the first sound acquisition module is arranged inside the shell and is in sound insulation with the outside of the equipment; the first sound acquisition module is used for acquiring an internal noise signal inside the equipment and sending the internal noise signal to the noise processing module;
the second sound acquisition module is used for acquiring a sound input signal outside the equipment and sending the sound input signal to the noise processing module; the noise processing module is also used for acquiring an external noise signal outside the equipment and sending the external noise signal to the noise processing module;
and the noise processing module is used for carrying out noise reduction processing on the sound input signal according to the external noise signal and the internal noise signal to obtain a target sound signal.
2. The apparatus of claim 1, wherein the noise processing module comprises: an external noise processing submodule and an internal noise processing submodule;
the external noise processing submodule is used for carrying out noise reduction processing on the sound input signal according to the external noise signal to obtain an external target sound signal;
and the internal noise processing submodule is used for carrying out noise reduction processing on the external target sound signal according to the internal noise signal to obtain the target sound signal.
3. The apparatus of claim 1, wherein the housing is acoustically insulating.
4. The device according to claim 1, wherein the second sound obtaining module is specifically configured to receive an initial sound signal input from the outside, and perform noise reduction processing on the initial sound signal to obtain the sound input signal.
5. The device of any of claims 1 to 4, wherein the noise processing module performs noise reduction processing using a fixed beam form or an adaptive filter.
6. The device of claim 4, wherein the first sound acquisition module performs noise reduction processing using a fixed beam form or an adaptive filter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920797332.5U CN210667779U (en) | 2019-05-29 | 2019-05-29 | Equipment capable of reducing noise |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920797332.5U CN210667779U (en) | 2019-05-29 | 2019-05-29 | Equipment capable of reducing noise |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN210667779U true CN210667779U (en) | 2020-06-02 |
Family
ID=70815577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201920797332.5U Active CN210667779U (en) | 2019-05-29 | 2019-05-29 | Equipment capable of reducing noise |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN210667779U (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110164425A (en) * | 2019-05-29 | 2019-08-23 | 北京声智科技有限公司 | A kind of noise-reduction method, device and the equipment that can realize noise reduction |
| CN112017678A (en) * | 2019-05-29 | 2020-12-01 | 北京声智科技有限公司 | Equipment capable of realizing noise reduction and noise reduction method and device thereof |
-
2019
- 2019-05-29 CN CN201920797332.5U patent/CN210667779U/en active Active
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110164425A (en) * | 2019-05-29 | 2019-08-23 | 北京声智科技有限公司 | A kind of noise-reduction method, device and the equipment that can realize noise reduction |
| CN112017678A (en) * | 2019-05-29 | 2020-12-01 | 北京声智科技有限公司 | Equipment capable of realizing noise reduction and noise reduction method and device thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107454508B (en) | TV set and TV system of microphone array | |
| US20200251119A1 (en) | Method and device for processing audio signal using audio filter having non-linear characterstics | |
| CN107221336A (en) | It is a kind of to strengthen the devices and methods therefor of target voice | |
| CN210667779U (en) | Equipment capable of reducing noise | |
| CN111133511A (en) | Sound source separation system | |
| WO2015065682A1 (en) | Selective audio source enhancement | |
| CN105810202B (en) | It is a kind of to drop hypoechoic method, apparatus and communication apparatus | |
| CN106663445A (en) | Voice processing device, voice processing method, and program | |
| CN103426433A (en) | Noise cancellation method | |
| CN103219012A (en) | Double-microphone noise elimination method and device based on sound source distance | |
| CN109920419A (en) | Sound control method and device, electronic equipment and computer-readable medium | |
| US9589572B2 (en) | Stepsize determination of adaptive filter for cancelling voice portion by combining open-loop and closed-loop approaches | |
| CN110660407B (en) | Audio processing method and device | |
| CN107068162A (en) | A kind of sound enhancement method, device and terminal device | |
| CN209845244U (en) | In-ear noise-reducing earphone | |
| CN112669805B (en) | Active noise control system of compressor in gas station based on equation error algorithm | |
| CN109616119A (en) | A kind of Multifunctional gateway equipment based on IPv6 agreement | |
| TW201701275A (en) | Front-end audio processing system | |
| CN109151237A (en) | The illumination-imitation projection self-adoptive echo cancel method attracted based on zero | |
| CN109935238B (en) | Echo cancellation method, device and terminal equipment | |
| WO2020238203A1 (en) | Noise reduction method, noise reduction apparatus, and device capable of reducing noise | |
| CN112017678A (en) | Equipment capable of realizing noise reduction and noise reduction method and device thereof | |
| CN113012709A (en) | Echo cancellation method and device | |
| CN207603830U (en) | A kind of household electrical appliance intelligent voice system | |
| CN107527622B (en) | A kind of variable step symbol subband acoustic echo removing method based on maximum entropy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |